---
title: fish-audio-s2-pro-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/fish-audio-s2-pro-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/fish-audio-s2-pro-8bit.md"
repository: mlx-community/fish-audio-s2-pro-8bit
last_updated: 2026-03-20
license: other
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - fish_qwen3_omni
base_model:
  - fishaudio/s2-pro
base_model_relation: quantized
parameters: 1.3B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
  - ja
  - ko
  - es
  - pt
  - ar
  - ru
  - fr
  - de
  - sv
  - it
  - tr
  - no
  - nl
  - cy
  - eu
  - ca
  - da
  - gl
  - ta
  - hu
  - fi
  - pl
  - et
  - hi
  - la
  - ur
  - th
  - vi
  - jv
  - bn
  - yo
  - cs
  - sw
  - he
  - ms
  - uk
  - id
  - kk
  - bg
  - lv
  - my
  - tl
  - sk
  - ne
  - fa
  - af
  - el
  - bo
  - hr
  - ro
  - sn
  - mi
  - yi
  - am
  - be
  - km
  - is
  - az
  - sd
  - br
  - sq
  - ps
  - mn
  - ht
  - ml
  - sr
  - sa
  - te
  - kn
  - si
  - hy
  - mr
  - as
  - gu
  - fo
downloads: 385
stars: 0
tags:
  - mlx
  - text-to-speech
  - speech
  - "speech generation"
  - "voice cloning"
  - tts
  - mlx-audio
---

# fish-audio-s2-pro-8bit

> fish-audio-s2-pro-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/fish-audio-s2-pro-8bit

mlx-community/fish-audio-s2-pro-8bit 是 ModelScope 魔搭社区上的 1.3B 参数text-to-speech模型，采用 other 许可，基于 fishaudio/s2-pro 构建。

- **Repository**: mlx-community/fish-audio-s2-pro-8bit
- **License**: other
- **Tasks**: text-to-speech
- **Parameters**: 1.3B
- **Base model**: fishaudio/s2-pro
- **Tags**: mlx, text-to-speech, speech, speech generation, voice cloning, tts, mlx-audio
- **Downloads**: 385
- **Stars**: 0
- **Last updated**: 2026-03-20

Source: https://www.modelscope.cn/models/mlx-community/fish-audio-s2-pro-8bit

---

# mlx-community/fish-audio-s2-pro-8bit

This model was converted to MLX format from [`fishaudio/s2-pro`](https://huggingface.co/fishaudio/s2-pro) using mlx-audio version **0.4.0**.

Refer to the [original model card](https://huggingface.co/fishaudio/s2-pro) for more details on the model.

## Model Overview

Fish Audio S2 Pro is a leading text-to-speech model with fine-grained inline control of prosody and emotion. Trained on **10M+ hours** of audio data across **80+ languages**, it combines reinforcement learning alignment with a Dual-Autoregressive architecture.

### Architecture

| Attribute | Value |
|-----------|-------|
| Total Parameters | 5B |
| Slow AR | 4B (time-axis, primary semantic codebook) |
| Fast AR | 400M (residual codebooks per time step) |
| Audio Codec | 10 codebooks @ ~21 Hz frame rate |
| Tensor Type | BF16 |

### Fine-Grained Inline Control

Localized control over speech generation using `[tag]` syntax with free-form textual descriptions (15,000+ supported tags):

```
[whisper in small voice]
[professional broadcast tone]
[pitch up]
```

**Common Tags (15,000+ supported):**
`[pause]` `[emphasis]` `[laughing]` `[inhale]` `[chuckle]` `[tsk]` `[singing]` `[excited]` `[volume up]` `[echo]` `[angry]` `[whisper]` `[screaming]` `[sad]` `[shocked]` and many more.

### Supported Languages

**Tier 1 (Full Support):** Japanese, English, Chinese
**Tier 2 (Strong Support):** Korean, Spanish, Portuguese, Arabic, Russian, French, German
**Additional:** 70+ more languages

## Use with mlx-audio

```bash
pip install -U mlx-audio
```

### CLI Example:
```bash
python -m mlx_audio.tts.generate --model mlx-community/fish-audio-s2-pro-8bit --text "Hello, this is a test."
```

### Python Example:
```python
from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio

model = load_model("mlx-community/fish-audio-s2-pro-8bit")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)
```

## Citation

```bibtex
@misc{liao2026fishaudios2technical,
      title={Fish Audio S2 Technical Report},
      author={Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han},
      year={2026},
      eprint={2603.08823},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2603.08823},
}
```

## License

This model is released under the **Fish Audio Research License**:
- Research use: Free
- Non-commercial use: Free
- Commercial use: Requires separate license from Fish Audio (contact: business@fish.audio)

See the [original model](https://huggingface.co/fishaudio/s2-pro) for full license details.